ISPRS Open Journal of Photogrammetry and Remote Sensing最新文献

{"title":"Domain adaptation of deep neural networks for tree part segmentation using synthetic forest trees","authors":"Mitch Bryson ,&nbsp;Ahalya Ravendran ,&nbsp;Celine Mercier ,&nbsp;Tancred Frickey ,&nbsp;Sadeepa Jayathunga ,&nbsp;Grant Pearse ,&nbsp;Robin J.L. Hartley","doi":"10.1016/j.ophoto.2024.100078","DOIUrl":"10.1016/j.ophoto.2024.100078","url":null,"abstract":"<div><div>Supervised deep learning algorithms have recently achieved state-of-the-art performance in the classification, segmentation and analysis of 3D LiDAR point cloud data in a wide-range of applications and environments. One of the main downsides of deep learning-based approaches is the need for extensive training datasets, <em>i.e</em>. LiDAR point clouds that have been annotated for target tasks by human experts. One strategy for addressing this issue is the use of simulated/synthetic data (with automatically generated annotations) for training models which can then be deployed on real target data/environments. This paper explores using synthetic data of realistic forest trees to train deep learning models for tree part segmentation from real forest LiDAR data. We develop a new pipeline for generating high-fidelity simulated LiDAR scans of synthetic forest trees and combine this with an unsupervised domain adaptation strategy to adapt models trained on synthetic data to LiDAR data captured in real forest environments.</div><div>Models were trained for semantic segmentation of tree parts using a PointNet++ architecture and evaluated across a range of medium to high-resolution laser scanning datasets collected across both ground-based and aerial platforms in multiple forest environments. Results of our work indicated that models trained on our synthetic data pipeline were competitive with models trained on real data, in particular when real data came from non-target sites, and our unsupervised domain adaptation method further improved performance. Our approach has implications for reducing the burden required in manual human expert annotation of large LiDAR datasets required to achieve high-performance from deep learning methods for forest analysis. The use of synthetically-trained models shown here provides a potential way to reduce the barriers to the use of deep learning in large-scale forest analysis, with implications to applications ranging from forest inventories to scaling-up in-situ forest phenotyping.</div></div>","PeriodicalId":100730,"journal":{"name":"ISPRS Open Journal of Photogrammetry and Remote Sensing","volume":"14 ","pages":"Article 100078"},"PeriodicalIF":0.0,"publicationDate":"2024-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142706287","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Colour guided ground-to-UAV fire segmentation","authors":"Rui Zhou,&nbsp;Tardi Tjahjadi","doi":"10.1016/j.ophoto.2024.100076","DOIUrl":"10.1016/j.ophoto.2024.100076","url":null,"abstract":"<div><div>Leveraging ground-annotated data for scene analysis on unmanned aerial vehicles (UAVs) can lead to valuable real-world applications. However, existing unsupervised domain adaptive (UDA) methods primarily focus on domain confusion, which raises conflicts among training data if there is a huge domain shift caused by variations in observation perspectives or locations. To illustrate this problem, we present a ground-to-UAV fire segmentation method as a novel benchmark to verify typical UDA methods, and propose an effective framework, Colour-Mix, to boost the performance of the segmentation method equivalent to the fully supervised level. First, we identify domain-invariant fire features by deriving fire-discriminating components (u*VS) defined in colour spaces Lu*v*, YUV, and HSV. Notably, we devise criteria to combine components that are beneficial for integrating colour signals into deep-learning training, thus significantly improving the generalisation abilities of the framework without resorting to UDA techniques. Second, we perform class-specific mixing to eliminate irrelevant background content on the ground scenario and enrich annotated fire samples for the UAV imagery. Third, we propose to disentangle the feature encoding for different domains and use class-specific mixing as robust training signals for the target domain. The framework is validated on the drone-captured dataset, Flame, by using the combined ground-level source datasets, Street Fire and Corsica Wildfires. The code is available at <span><span>https://github.com/Rui-Zhou-2/Colour-Mix</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":100730,"journal":{"name":"ISPRS Open Journal of Photogrammetry and Remote Sensing","volume":"14 ","pages":"Article 100076"},"PeriodicalIF":0.0,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142656293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Measuring nearshore waves at break point in 4D with Stereo-GoPro photogrammetry: A field comparison with multi-beam LiDAR and pressure sensors","authors":"Marion Jaud ,&nbsp;Stéphane Bertin ,&nbsp;Emmanuel Augereau ,&nbsp;France Floc’h","doi":"10.1016/j.ophoto.2024.100077","DOIUrl":"10.1016/j.ophoto.2024.100077","url":null,"abstract":"<div><div>Measuring nearshore waves remains technically challenging despite wave properties are being used in a variety of applications. With the promise of high-resolution and remotely-sensed measurements of water surfaces in four dimensions (spatially and temporally), stereo-photogrammetry applied to video imagery has grown as a viable solution over the last ten years. However, past deployments have essentially used costly cameras and optics, requiring fixed deployment platforms and hindering the applicability of the method in the field.</div><div>Focusing on close-range measurements of nearshore waves at break point, this paper presents a detailed evaluation of a field-oriented and cost-effective stereo-video system composed of two <em>GoPro</em>^<em>TM</em> <em>(Hero 7)</em> cameras capable of collecting 12-megapixel imagery at 24 frames per second. The so-called ‘Stereo-GoPro’ system was deployed in the surf zone during energetic conditions at a macrotidal field site using a custom-assembled mobile tower. Deployed concurrently with stereo-video, a 16-beam LiDAR (Light Detection and Ranging) and two pressure sensors provided independent data to assess stereo-GoPro performance. All three methods were compared with respect to the evolution of the free-surface elevation over 25 min of recording at high tide and the wave parameters derived from spectral analysis. We show that stereo-GoPro allows producing digital elevation models (DEMs) of the water surface over large areas (250 m²) at high spatial resolution (0.2 m grid size), which was unsurpassed by the LiDAR. From instrument inter-comparisons at the location of the pressure transducers, free-surface elevation root-mean square errors of 0.11 m and 0.18 m were obtained respectively for LiDAR and stereo-GoPro. This translated into a maximum relative error of 3.9% and 12.5% on spectral wave parameters for LiDAR and stereo-GoPro, respectively. Optical distortion in imagery, which could not be completely corrected with calibration, was the main source of error. Whilst stereo-video processing workflow remains complex, cost-effective stereo-photogrammetry already opens new opportunities for deriving wave parameters in coastal regions, as well as for various other practical applications. Further tests should try to address specifically challenges associated to variable ambient conditions and acquisition configurations, affecting measurement performance, to guarantee a larger uptake of the technique.</div></div>","PeriodicalId":100730,"journal":{"name":"ISPRS Open Journal of Photogrammetry and Remote Sensing","volume":"14 ","pages":"Article 100077"},"PeriodicalIF":0.0,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142656283","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated extrinsic calibration of solid-state frame LiDAR sensors with non-overlapping field of view for monitoring indoor stockpile storage facilities","authors":"Mina Joseph ,&nbsp;Haydn Malackowski ,&nbsp;Hazem Hanafy ,&nbsp;Jidong Liu ,&nbsp;Zach DeLoach ,&nbsp;Darcy Bullock ,&nbsp;Ayman Habib","doi":"10.1016/j.ophoto.2024.100073","DOIUrl":"10.1016/j.ophoto.2024.100073","url":null,"abstract":"<div><p>Several industrial and commercial bulk material management applications rely on accurate, current stockpile volume estimation. Proximal imaging and LiDAR sensing modalities can be used to derive stockpile volume estimates in outdoor and indoor storage facilities. Among available imaging and LiDAR sensing modalities, the latter is more advantageous for indoor storage facilities due to its ability to capture scans under poor lighting conditions. Evaluating volumes from such sensing modalities requires the pose (i.e., position and orientation) parameters of the used sensors relative to a common reference frame. For outdoor facilities, a Global Navigation Satellite System (GNSS) combined with an Inertial Navigation System (INS) can be used to derive the sensors’ pose relative to a global reference frame. For indoor facilities, GNSS signal outages will not allow for such capability. Prior research has developed strategies for establishing the sensor position and orientation for stockpile volume estimation while relying on multi-beam spinning LiDAR units. These approaches are feasible due to the large range and Field of View (FOV) of such systems that can capture the internal surfaces of indoor storage facilities.</p><p>The mechanical movement of multi-beam spinning LiDAR units together with the harsh conditions within indoor facilities (e.g., excessive humidity, wide range of temperature variation, dust, and corrosive environment in deicing salt storage facilities) limit the use of such systems. With the increasing availability of solid-state LiDAR units, there is an interest in exploring their potential for stockpile volume estimation. Despite their higher robustness to harsh conditions, solid-state LiDAR units have shorter distance measurement range and limited FOV when compared with multi-beam spinning LiDAR. This research presents a strategy for the extrinsic calibration (i.e., estimating the relative pose parameters) of installed solid-state LiDAR units inside stockpile storage facilities. The extrinsic calibration is made possible using deployed spherical targets and a complete, reference scan of the facility from another LiDAR sensing modality. The proposed research introduces strategies for: 1) automated extraction of the spherical targets; 2) automated matching of these targets in the solid-state LiDAR and reference scans using invariant relationships among them; and 3) coarse-to-fine estimation of the calibration parameters. Experimental results in several facilities have shown the feasibility of using the proposed methodology to conduct the extrinsic calibration and volume evaluation with an error percentage less than 3.5% even with occlusion percentages reaching up to 50%.</p></div>","PeriodicalId":100730,"journal":{"name":"ISPRS Open Journal of Photogrammetry and Remote Sensing","volume":"13 ","pages":"Article 100073"},"PeriodicalIF":0.0,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667393224000176/pdfft?md5=0f0d8b437518bd5c7f1f1f0eb89fbdab&pid=1-s2.0-S2667393224000176-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142097901","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Robust marker detection and identification using deep learning in underwater images for close range photogrammetry","authors":"Jost Wittmann ,&nbsp;Sangam Chatterjee ,&nbsp;Thomas Sure","doi":"10.1016/j.ophoto.2024.100072","DOIUrl":"10.1016/j.ophoto.2024.100072","url":null,"abstract":"<div><p>The progressing industrialization of oceans mandates reliable, accurate and automatable subsea survey methods. Close-range photogrammetry is a promising discipline, which is frequently applied by archaeologists, fish-farmers, and the offshore energy industry. This paper presents a robust approach for the reliable detection and identification of photogrammetric markers in subsea images. The proposed method is robust to severe image degradation, which is frequently observed in underwater images due to turbidity, light absorption, and optical aberrations. This is the first step towards a highly automated work-flow for single-camera underwater photogrammetry. The newly developed approach comprises several machine learning models, which are trained by 10,122 real-world subsea images, showing a total of 338,301 photogrammetric markers. The performance is evaluated using an object detection metrics, and through a comparison with the commercially available software Metashape by Agisoft. Metashape delivers satisfactory results when the image quality is good. In images with strong noise, haze or little light, only the novel approach retrieves sufficient information for a high degree of automation of the subsequent bundle adjustment. While the need for offshore personnel and the time-to-results decreases, the robustness of the survey increases.</p></div>","PeriodicalId":100730,"journal":{"name":"ISPRS Open Journal of Photogrammetry and Remote Sensing","volume":"13 ","pages":"Article 100072"},"PeriodicalIF":0.0,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667393224000164/pdfft?md5=2fb00797de66c6b69489c851a71accbe&pid=1-s2.0-S2667393224000164-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142168606","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Target-based georeferencing of terrestrial radar images using TLS point clouds and multi-modal corner reflectors in geomonitoring applications","authors":"Lorenz Schmid ,&nbsp;Tomislav Medic ,&nbsp;Othmar Frey ,&nbsp;Andreas Wieser","doi":"10.1016/j.ophoto.2024.100074","DOIUrl":"10.1016/j.ophoto.2024.100074","url":null,"abstract":"<div><div>Terrestrial Radar Interferometry (TRI) is widely adopted in geomonitoring applications due to its capability to precisely observe surface displacements along the line of sight, among other key characteristics. As its deployment grows, TRI is also increasingly used to monitor smaller and more dispersed geological phenomena, where the challenge is their precise localization in 3d space if the pose of the radar interferometer is not known beforehand. To tackle this challenge, we introduce a semi-automatic target-based georeferencing method for precisely aligning TRI data with 3d point clouds obtained using long-range Terrestrial Laser Scanning (TLS). To facilitate this, we developed a multi-modal corner reflector (mmCR) that serves as a common reference point recognizable by both technologies, and we accompanied it with a semi-automatic data-processing pipeline, including the algorithms for precise center estimation. Experimental validation demonstrated that the corner reflector can be localized within the TLS data with a precision of 3–5 cm and within the TRI data with 1–2 dm. The targets were deployed in a realistic geomonitoring scenario to evaluate the implemented workflow and the achievable quality of georeferencing. The post-georeferencing mapping uncertainty was found to be on a decimeter level, matching the state-of-the-art results using dedicated targets and achieving more than an order of magnitude lower uncertainty than the existing data-driven approaches. In contrast to the existing target-based approaches, our results were achieved without laborious visual data inspection and manual target detection and on significantly larger distances, surpassing 2 km. The use of the developed mmCR and its associated data-processing pipeline extends beyond precise georeferencing of TRI imagery to TLS point clouds, allowing for alternatively georeferencing using total stations, mapping quality evaluation as well as on-site testing and calibrating TRI systems within the application environment.</div></div>","PeriodicalId":100730,"journal":{"name":"ISPRS Open Journal of Photogrammetry and Remote Sensing","volume":"13 ","pages":"Article 100074"},"PeriodicalIF":0.0,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142319534","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Erratum to “Principled bundle block adjustment with multi-head cameras” [ISPRS Open J. Photogram. Rem. Sens. 11 (2023) 100051]","authors":"Eleonora Maset,&nbsp;Luca Magri,&nbsp;Andrea Fusiello","doi":"10.1016/j.ophoto.2024.100068","DOIUrl":"10.1016/j.ophoto.2024.100068","url":null,"abstract":"","PeriodicalId":100730,"journal":{"name":"ISPRS Open Journal of Photogrammetry and Remote Sensing","volume":"13 ","pages":"Article 100068"},"PeriodicalIF":0.0,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142422095","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Erratum to “Comparison of neural networks and k-nearest neighbors methods in forest stand variable estimation using airborne laser data” [ISPRS Open J. Photogram. Rem. Sens. 4 (2022) 100012]","authors":"Andras Balazs,&nbsp;Eero Liski,&nbsp;Sakari Tuominen,&nbsp;Annika Kangas","doi":"10.1016/j.ophoto.2024.100066","DOIUrl":"10.1016/j.ophoto.2024.100066","url":null,"abstract":"","PeriodicalId":100730,"journal":{"name":"ISPRS Open Journal of Photogrammetry and Remote Sensing","volume":"13 ","pages":"Article 100066"},"PeriodicalIF":0.0,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142422093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Erratum to “Individual tree segmentation and species classification using high-density close-range multispectral laser scanning data” [ISPRS Open J. Photogram. Rem. Sens. 9 (2023) 100039]","authors":"Aada Hakula,&nbsp;Lassi Ruoppa,&nbsp;Matti Lehtomäki,&nbsp;Xiaowei Yu,&nbsp;Antero Kukko,&nbsp;Harri Kaartinen,&nbsp;Josef Taher,&nbsp;Leena Matikainen,&nbsp;Eric Hyyppä,&nbsp;Ville Luoma,&nbsp;Markus Holopainen,&nbsp;Ville Kankare,&nbsp;Juha Hyyppä","doi":"10.1016/j.ophoto.2024.100067","DOIUrl":"10.1016/j.ophoto.2024.100067","url":null,"abstract":"","PeriodicalId":100730,"journal":{"name":"ISPRS Open Journal of Photogrammetry and Remote Sensing","volume":"13 ","pages":"Article 100067"},"PeriodicalIF":0.0,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142422094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Individual tree detection and crown delineation in the Harz National Park from 2009 to 2022 using mask R–CNN and aerial imagery","authors":"Moritz Lucas ,&nbsp;Maren Pukrop ,&nbsp;Philip Beckschäfer ,&nbsp;Björn Waske","doi":"10.1016/j.ophoto.2024.100071","DOIUrl":"https://doi.org/10.1016/j.ophoto.2024.100071","url":null,"abstract":"<div><p>Forest diebacks pose a major threat to global ecosystems. Identifying and mapping both living and dead trees is crucial for understanding the causes and implementing effective management strategies. This study explores the efficacy of Mask R–CNN for automated forest dieback monitoring. The method detects individual trees, delineates their crowns, and classifies them as alive or dead. We evaluated the approach using aerial imagery and canopy height models in the Harz Mountains, Germany, a region severely affected by forest dieback. To assess the model's ability to track changes over time, we applied it to images from three separate flight campaigns (2009, 2016, and 2022). This evaluation considered variations in acquisition dates, cameras, post-processing techniques, and image tilting. Forest changes were analyzed based on the detected trees' number, spatial distribution, and height. A comprehensive accuracy assessment demonstrated the Mask R–CNN's robust performance, with precision scores ranging from 0.80 to 0.88 and F1-scores from 0.88 to 0.91. These results confirm the model's ability to generalize across diverse image acquisition conditions. While minor changes were observed between 2009 and 2016, the period between 2016 and 2022 witnessed substantial dieback, with a 64.57% loss of living trees. Notably, taller trees appeared to be particularly affected. This study highlights Mask R–CNN's potential as a valuable tool for automated forest dieback monitoring. It enables efficient detection, delineation, and classification of both living and dead trees, providing crucial data for informed forest management practices.</p></div>","PeriodicalId":100730,"journal":{"name":"ISPRS Open Journal of Photogrammetry and Remote Sensing","volume":"13 ","pages":"Article 100071"},"PeriodicalIF":0.0,"publicationDate":"2024-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667393224000152/pdfft?md5=71f4c32c472a325cebf9fb59433deb61&pid=1-s2.0-S2667393224000152-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141596887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}